python - How to get all text between just two specified tags using BeautifulSoup?

Question

html = """
...
<tt class="descname">all</tt>
<big>(</big>
<em>iterable</em>
<big>)</big>
<a class="headerlink" href="#all" title="Permalink to this definition">?</a>
...
"""

I want to get all text between starting tag big upto before the first occurrence of a tag. This means if I take this example, then i must get (iterable) as a string.

Answer 1

An iterative approach.

from BeautifulSoup import BeautifulSoup as bs
from itertools import takewhile, chain

def get_text(html, from_tag, until_tag):
    soup = bs(html)
    for big in soup(from_tag):
        until = big.findNext(until_tag)
        strings = (node for node in big.nextSiblingGenerator() if getattr(node, 'text', '').strip())
        selected = takewhile(lambda node: node != until, strings)
        try:
            yield ''.join(getattr(node, 'text', '') for node in chain([big, next(selected)], selected))
        except StopIteration as e:
            pass

for text in get_text(html, 'big', 'a'):
    print text